Initializing array made of 33554432 64-bit words (256.00 MiB).
Source pages allocated with transparent hugepages: 100.0% (65536 pages, 100.0% flagged)
Legend:
  BandW: Implied bandwidth (assuming 64-byte cache line) in MB/s
  % Eff: Effectiness of this lane count compared to the prior, as a % of ideal
  Speedup: Speedup factor for this many lanes versus one lane
Applying Sattolo's algorithm... chain total: 33554432
Time to sum up the array (linear scan) 0.020 s (x 8 = 0.159 s), bandwidth = 12872.1 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     4.238391        483     126.3       0%        1.0
           2     2.062914        993      61.5     103%        2.1
           3     1.331738       1538      39.7     106%        3.2
           4     0.969993       2111      28.9     109%        4.4
           5     0.769055       2663      22.9     104%        5.5
           6     0.623408       3285      18.6     114%        6.8
           7     0.538940       3800      16.1      95%        7.9
           8     0.475223       4310      14.2      95%        8.9
           9     0.417405       4907      12.4     109%       10.2
          10     0.372383       5500      11.1     108%       11.4
          11     0.344404       5946      10.3      83%       12.3
          12     0.325326       6295       9.7      66%       13.0
          13     0.305507       6704       9.1      79%       13.9
          14     0.291926       7015       8.7      62%       14.5
          15     0.282317       7254       8.4      49%       15.0
          16     0.275727       7428       8.2      37%       15.4
          17     0.276081       7418       8.2      -2%       15.4
          18     0.268233       7635       8.0      51%       15.8
          19     0.269429       7601       8.0      -8%       15.7
          20     0.259740       7885       7.7      72%       16.3
          21     0.263685       7767       7.9     -32%       16.1
          22     0.259617       7889       7.7      34%       16.3
          23     0.257380       7957       7.7      20%       16.5
          24     0.255990       8000       7.6      13%       16.6
          25     0.259284       7899       7.7     -32%       16.3
          26     0.261932       7819       7.8     -27%       16.2
          27     0.257286       7960       7.7      48%       16.5
          28     0.259493       7892       7.7     -24%       16.3
          29     0.259036       7906       7.7       5%       16.4
          30     0.257633       7949       7.7      16%       16.5
          31     0.257565       7951       7.7       1%       16.5
          32     0.255456       8017       7.6      26%       16.6
          33     0.255644       8011       7.6      -2%       16.6
          34     0.264150       7753       7.9    -113%       16.0
          35     0.259343       7897       7.7      64%       16.3
          36     0.255119       8028       7.6      59%       16.6
          37     0.257661       7948       7.7     -37%       16.4
          38     0.255882       8004       7.6      26%       16.6
          39     0.258984       7908       7.7     -47%       16.4
          40     0.255759       8008       7.6      50%       16.6
Maybe you have about 16 parallel paths? 
exit=0
